Magnite (magnite.com) for agents: Browse the Magnite blog listing; Search the Magnite site for content; Read a page on magnite.com — through Unbrowse's scoped MCP for magnite.com (unofficial), which...
Magnite as tools for your agent. Unofficial: not affiliated with or endorsed by magnite.com. Unbrowse compiled these from magnite.com's own requests: each call replays the site's first-party API server-side and returns a verified result. No scraping of rendered pages, no browser on your side, no magnite.com API key.
This server is a tool scope holding only magnite.com: its compiled tools plus the Unbrowse tools that run them, so the agent's tool list stays small and every call stays on magnite.com.
claude mcp add --transport http magnite https://unbrowse.ai/mcp/magnite.com
codex mcp add magnite --url https://unbrowse.ai/mcp/magnite.com && codex mcp login magnite
{"mcpServers":{"magnite":{"url":"https://unbrowse.ai/mcp/magnite.com"}}}
The first connect signs in to Unbrowse with OAuth (free tier, only verified results count). For scripts, send Authorization: Bearer $UNBROWSE_API_KEY (key from https://unbrowse.ai/app/keys; keep it in a secret manager, never in config you commit).
If none of the tools below are in this session's tool list, the server is not connected or not signed in: say so and stop. Do not fetch magnite.com some other way and present it as this skill's result.
magnite_com__get_wp_posts — Browse the Magnite blog listingBrowse the Magnite blog listing. No inputs. Returns data. Read-only on magnite.com.
categories (integer) — optional, e.g. "1"per_page (integer) — optional, e.g. "9"page (integer) — optional, e.g. "1"{"categories":1,"per_page":9,"page":1}
magnite_com__get_root — Search the Magnite site for contentSearch the Magnite site for content. Inputs: s. Returns the page's title, readable text and links. Read-only on magnite.com.
s (string, required){"s":"<s>"}
magnite_com__read_page — Read a page on magnite.comRead any page on magnite.com — a path such as /news/2026/some-story, or a full magnite.com URL — and get its title, readable text and links. One first-party HTTP request, no browser. Follow a returned link by passing its href back as the path. Inputs: path e.g. "/". Returns the page's title, readable text and links. Read-only on magnite.com.
path (string, required) — A page on magnite.com: a path like /about, or a full URL on magnite.com{"path":"/"}
Always there too: unbrowse.run (a task on magnite.com in plain words), unbrowse.inspect, unbrowse.resume, unbrowse.scrape and unbrowse.map (any page on magnite.com), and the recorded cloud browser unbrowse.browse.open → unbrowse.browse.act → unbrowse.browse.finish. Hosts that reject dotted names show them with _ (unbrowse_run).
status. succeeded carries the verified result. input_required is not a failure: answer the open fields with unbrowse.resume {runId, answers} on the same run.unbrowse.run {task}. It fails with no_capability when nothing is compiled for that yet: do it once with unbrowse.browse.open on magnite.com → unbrowse.browse.act → unbrowse.browse.finish, which compiles a new tool this server lists next time. Anything off magnite.com is refused here (not_in_scope): use the general Unbrowse server for that.unbrowse.browse.act with action: "autofill" fills magnite.com's login from their Unbrowse password manager.succeeded result says. outcome_unknown means a change may have happened: check before retrying. Posting, buying, sending or deleting needs the user's go-ahead.Every tool is also a REST call:
curl -s https://unbrowse.ai/api/v1/sites/magnite.com/call/magnite_com__get_wp_posts \
-H "authorization: Bearer $UNBROWSE_API_KEY" -H "content-type: application/json" \
-d '{"categories":1,"per_page":9,"page":1}'
OpenAPI: https://unbrowse.ai/api/v1/sites/magnite.com/openapi.json. Every other site: the general Unbrowse skill (https://github.com/unbrowse-ai/unbrowse) and https://unbrowse.ai/mcp.